<h3 id="to-the-mod-teamtos-disclaimer">To the mod team/TOS disclaimer</h3><p></p><p>This model complies with the TOS to the best of my knowledge. For it to operate the person must already be in a sexual scenario(eg a woman with a strap on and a man's anus must be in the scene). It, by itself, does not add a nudity into the scene. None of the training material included anything that took a person and moved them into a sexual scenario, it all started with both man and woman in the scene. As always happy to show the training material to the mod team if that helps at all.</p><p></p><h3 id="concept">Concept</h3><p></p><p>A woman wearing a strap on dildo having anal sex with a man. Only covered side view, no POV angles were used so it probably doesn't do that well.</p><p></p><p>This was a request by <a target="_blank" rel="ugc" href="https://civarchive.com/user/ThrowawayAccoun42414">@ThrowawayAccoun42414</a>. I used <a target="_blank" rel="ugc" href="https://civarchive.com/user/playtime_ai_/">@playtime_ai_ </a>excellent strap on lora to prep the images for I2V.</p><p></p><h3 id="usage">Usage</h3><p></p><p>Base prompt is:</p><pre><code>A video of a woman pegging a man.a woman and a man engaging in anal sex.</code></pre><p>If they are facing each other add:</p><pre><code>They are facing each other.</code></pre><p>Otherwise add:</p><pre><code>The man is facing away from the woman.</code></pre><p>The model was trained with fairly detailed captions so should be able to describe other actions happening, like the woman's breasts moving or the man's penis being grabbed etc.</p><p></p><h3 id="training">Training</h3><p></p><p>The model was trained on 40 videos, 20 facing and 20 reverse, all 5 seconds long and 16 fps. High noise was trained at 320 resolution with 4 frame buckets. Low noise was 704 resolution with 2 frame buckets. 30 Epochs at 4 batch for High, 20 epochs and 2 batch for low. All trained on diffusion pipe on 4x3090s. Captioning was automated using JoyCaption and DarkAges Llama 70B.</p><p></p>

Files with SHA256: 7998b16d0681e23c15515c0af5fbd493a2e810e4ec80cfc03ddc4a7690204bd8